Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms

Authors:
Wen Yu
Affiliations:
Departamento de Control Automatico, CINVESTAV-IPN, A.P. 14-740, Av. IPN 2508, México D.F. 07360, Mexico
Venue:
Information Sciences—Informatics and Computer Science: An International Journal - Special issue: Informatics and computer science intelligent systems applications
Year:
2004

Citing 12
Cited 26

SuperSAB: fast adaptive back propagation with good scaling properties

Neural Networks
Neurofuzzy adaptive modelling and control

Neurofuzzy adaptive modelling and control
Robust adaptive control

Robust adaptive control
Identification of nonlinear dynamical systems using multilayered neural networks

Automatica (Journal of IFAC)
Stable Adaptive Neural Network Control

Stable Adaptive Neural Network Control
Stability of Adaptive Controllers

Stability of Adaptive Controllers
NLq theory: checking and imposing stability of recurrentneural networks for nonlinear modeling

IEEE Transactions on Signal Processing
Input-to-state stability for discrete-time nonlinear systems

Automatica (Journal of IFAC)
Multilayer neural-net robot controller with guaranteed tracking performance

IEEE Transactions on Neural Networks
Stable dynamic backpropagation learning in recurrent neural networks

IEEE Transactions on Neural Networks
Some new results on system identification with dynamic neural networks

IEEE Transactions on Neural Networks
High-order neural network structures for identification of dynamical systems

IEEE Transactions on Neural Networks

A novel deniable authentication protocol using generalized ElGamal signature scheme

Information Sciences: an International Journal
A channel equalizer using reduced decision feedback Chebyshev functional link artificial neural networks

Information Sciences: an International Journal
Indirect adaptive control of nonlinear dynamic systems using self recurrent wavelet neural networks via adaptive learning rates

Information Sciences: an International Journal
Nonlinear system identification with recurrent neural networks and dead-zone Kalman filter algorithm

Neurocomputing
Locally recurrent neural networks for wind speed prediction using spatial correlation

Information Sciences: an International Journal
Neural Networks Training with Optimal Bounded Ellipsoid Algorithm

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Stable Learning Algorithm of Global Neural Network for Identification of Dynamic Complex Systems

ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Nonlinear system identification with a feedforward neural network and an optimal bounded ellipsoid algorithm

WSEAS Transactions on Computers
Batch type local search-based adaptive neuro-fuzzy inference system (ANFIS) with self-feedbacks for time-series prediction

Neurocomputing
Nonlinear system identification using optimized dynamic neural network

Neurocomputing
Novel robust stability criteria of discrete-time stochastic recurrent neural networks with time delay

Neurocomputing
Delay-distribution-dependent stability of stochastic discrete-time neural networks with randomly mixed time-varying delays

Neurocomputing
Recurrent neural networks training with stable bounding ellipsoid algorithm

IEEE Transactions on Neural Networks
A generalized procedure in designing recurrent neural network identification and control of time-varying-delayed nonlinear dynamic systems

Neurocomputing
Fault diagnosis of underwater robots based on recurrent neural network

ROBIO'09 Proceedings of the 2009 international conference on Robotics and biomimetics
A recurrent neuro-fuzzy system and its application in inferential sensing

Applied Soft Computing
Bone age cluster assessment and feature clustering analysis based on phalangeal image rough segmentation

Pattern Recognition
Identification of nonlinear systems with outliers using wavelet neural networks based on annealing dynamical learning algorithm

Engineering Applications of Artificial Intelligence
Discrete time nonlinear identification via recurrent high order neural networks for a three phase induction motor

ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I
Boundedness and convergence of batch back-propagation algorithm with penalty for feedforward neural networks

Neurocomputing
Adaptive dynamic programming-based optimal control of unknown nonaffine nonlinear discrete-time systems with proof of convergence

Neurocomputing
Integration of support vector regression and annealing dynamical learning algorithm for MIMO system identification

Expert Systems with Applications: An International Journal
Exponential synchronization of memristor-based recurrent neural networks with time delays

Neurocomputing
Two Types of Haar Wavelet Neural Networks for Nonlinear System Identification

Neural Processing Letters
Study on landslide deformation prediction based on recurrent neural network under the function of rainfall

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part IV
Letters: A generalized indirect adaptive neural networks backstepping control procedure for a class of non-affine nonlinear systems with pure-feedback prototype

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In general, neural networks cannot match nonlinear systems exactly. Neuro identifier has to include robust modification in order to guarantee Lyapunov stability. In this paper input-to-state stability approach is applied to access robust training algorithms of discrete-time recurrent neural networks. We conclude that for nonlinear system identification, the gradient descent law and the backpropagation-like algorithm for the weights adjustment are stable in the sense of L∞ and robust to any bounded uncertainties.